Kuba

Code release: We open-source CliqueFlowmer — a full pipeline for offline materials optimization. Includes: • training + inference • latent optimization (evolution strategies) • decoding to crystal structures github.com/znowu/CliqueFl…

AI can optimize materials 🤘 Our (@pabbeel, @svlevine, @AIatMeta) proposed transformer model 𝗖𝗹𝗶𝗾𝘂𝗲𝗙𝗹𝗼𝘄𝗺𝗲𝗿, combined with 𝗲𝘃𝗼𝗹𝘂𝘁𝗶𝗼𝗻 strategies, discovers materials that optimize target properties. arxiv.org/abs/2603.06082

@teortaxesTex @_AndrewZhao @Benjamin_eecs Thanks man! As you know, papers’ contributions are not only their names, and if you read them, you learn they’re very different. From our perspective, their buffer curation is far off from self-play. But no other data - I grant them that! Peace ✌🏿

sorry Meta "superintelligence" lab but @_AndrewZhao et al. did this better and you don't cite them. Actually, many have (eg @Benjamin_eecs), whether joint maximization or minimax, verifiers or RMs. Why kang of a breakthrough? Good job evaluating on Vicuna tho, peak 2023 llamacore

LLMs that learn without data 🤯 No new datasets. No human demos. Just a model playing against itself—getting smarter every round. We call it Language Self-Play. Full paper arxiv.org/pdf/2509.07414 Thanks @metaai and @berkeley_ai

"Better than what's known" - the dream of AI in model-based optimization. Excited to present my paper with @pabbeel & @svlevine on Functional Graphical Models (arxiv.org/pdf/2401.05442) giving theoretical foundations for chasing that dream, at @aistats_conf ! #aistats_conf #ai

Deep RL has been driven by improvements in handcrafted algorithms. Our NeurIPS 2022 paper, “Discovered Policy Optimisation” instead meta-learns in a space of theoretically-sound algorithms and beats PPO on unseen tasks! w/ @kuba_AI @_aletcher @Luke_Metz @casdewitt @j_foerst 🧵

It takes @PiotrTempczyk , my first AI mentor, and his team to make true breakthroughs in ML; presented gloriously in the paper arxiv.org/pdf/2206.14882… at #ICML2022 in the long-talk fashion!